Search Results for: computer science

ABSTRACT
Performance evaluation of students in institution is a necessity and this is done based on the Grading system adopted by a school. Computation of Grade point average GPA is done manually and this is time consuming and tedious. This project views the present system of computing GPA and attempts to convert the process from the manual one into a computerized one in order to reduce time spent in computing students GPA especially in the final year. Microsoft Visual BASIC programming language was used because of its powerful features.

CHAPTER ONE
1.0 INTRODUCTION
1.1BACKGROUND OF THE STUDY
Evaluation is the systematic determination of merit, worth and significance of something or someone. Evaluation often is used to characterize and examine subjects of interest in a wide range of human enterprise including the Arts, business, Computer Science, criminal justice, foundation and nonprofit organizations, government and other human services. Performance Evaluation is a necessity for organizations, institutions and even individuals due to the fact that it helps them to know how they are faring and to know if there is any need for improvement. This research work is going focus on performance evaluation of students. In schools students are evaluated and their result is compared based on the Grading system adopted by a particular school. Some schools adopt the 4point Grading system while others operate on the 5point Grading system for evaluating student performance and computing their Grade Point Average GPA. However, most schools use the conventional manual system for computing the GPA of students. There have been numerous problems associated with the conventional system of computation.

1.2STATEMENT OF PROBLEMS
The following are the problems encountered with the use of conventional systems,
1. Manual computation of Grade point average
2. The work involved in the calculation of GPA is tedious especially when handling a large class.
3. A lot of time is exhausted and wasted in the process of computing while ensuring accuracy.
4. Most students cannot calculation their GPA.

1.3OBJECTIVE OF THE STUDY
The objective of this study is to develop an automated student performance evaluation system that will be able to eliminate the problems associated with the conventional system for evaluating and computing grade point average GPA of students. The study seek to design a prototype system for evaluating student performance using Visual Basic programming language that will provide facilities that will,
1. Compute students GPA faster and accurately
2. Compute the GPA at various levels
3. Compute the cumulative GPA CGPA
4. State the class of Honours a student falls into
5. Enable students to be able to compute their GPA easily

Abstract

This thesis presents research and study ofload balancing algorithms and the analysis of the performance of each algorithm in varying conditions. The research also covers a study of the characteristics of Internet traffic and its statistical properties. The network workload models that were implemented in the simulation program were derived from the many works already published within the Internet community. These workload models were successfully implemented and statistical proof is given that they exhibit characteristics similar to the workloads found on the Internet. Finally, this thesis compares and contrasts the differences between stateless server selection methods and state-base selection methods with the different algorithms studied.

INTRODUCTION

The research and results of the topic of Load Balancing and Internet traffic modeling are presented in this thesis.

Load Balancing is a form of system performance evaluation, analysis and optimization, which attempts to distribute a number of logical processes across a network of processing elements. There have been many algorithms and techniques that have been developed and studied for improving system performance. In early research in the field of computer science, the main focus for improving performance was to develop algorithms and techniques to optimize the use of systems with limited and expensive resources for scientific computing and information systems. Later, there was an emphasis on how to network groups of computers or workstations and then share the resources among workgroups. More recently there has been a tremendous increase in the popularity of the Internet as a system for sharing and gathering information. The use of the Internet has been increasing at a tremendous rate and there always has been a concern among those in the Internet community that enough resources will be available to provide the expected quality of service that is received by its users.

The process of balancing, sharing, scheduling or distributing work using a network of computers or a system of multiple processing elements is a widely studied sub

ject. This paper will focus on recent works that have been written regarding todays computing environments.

In this thesis, we will look at the art of load balancing and how it can be applied to distributed networks and more specifically the Internet. Initially, the focus of the research for this thesis was on development and analysis of algorithms that minimized the amount of messaging or probing that is required for determining the current workload of a set of processing elements, such as a group of replicated web servers. These algorithms were to compare stochastic based methods of estimating server workloads, with more intrusive methods of messaging and probing. During the process of developing the simulator to be used for evaluating the algorithms in this study, tasks related to modeling network workloads, and the workloads related to the Internet in particular, were identified to be crucial to the research in this area and as a result of this effort, network modeling has become a significant portion of this thesis.

The thesis is divided into the following chapters. Chapter 2 will discuss the concepts and research related to the subject of Load Balancing. Chapter 3 will discuss the issues related to modeling network traffic and in particular Internet traffic. Chapter 4 describes the Network Simulator used to evaluate the load balancing algorithms. Chapter 5 is the Experimental Design of the network simulations, and Chapter 6 will discuss the results of the experimental simulations. Finally, Chapter 7 will discuss the conclusions based upon the experiments performed in this study.

Finally, in addition to the goals already mentioned, it is the hope of the author that this research can be used as a reference for the continued study in the areas of network performance evaluation, modeling and simulation.

LOAD BALANCING

Load balancing is probably the most commonly used term for describing a class of processes that attempt to optimize system performance. System performance is optimized by attempting to best utilize a group of processing elements, typically a CPU, or storage elements, such as memory of disk, or some other resource that are interconnected in a distributed network. The process of Load Balancing may also be known as Load Sharing, Load Distribution, Parallel Programming, Concurrent Programming, and Control Scheduling. Although these processes can be quite different in their purpose, the processes all have a common goal. This goal is to allocate logical processes evenly across multiple processors, or a distributed network of processing elements, so that collectively all the logical processes are executed in the most efficient manner possible. Examples of some of the approaches for achieving this goal are: keeping idle systems busy, low execution latency fast execution time, fast response time, maximizing job throughput, executing jobs in parallel and distribution of jobs to specialized systems. More generally, whenever a processing element becomes idle and there are logical processes waiting for servers, the system should attempt to place any new process or processes waiting for service on an idle server and not on a busy one.

One area that has received a lot of research is the dynamic load balancing of processes by migrating processes from busy servers to less busy servers. The issues of

dynamic load balancing along with the basic load balancing concepts will be addressed in this chapter.

The rest of this chapter is divided into the following sections, the Types of Load Balancing, Selection Methods, Related Works and finally, Applications of Load Balancing.

2.1Types of Load Balancing

There are basically two types of load balancing, static load balancing and dynamic load balancing. The following two sections will discuss these topics.

2.1.1Static Load Balancing

Static load balancing is the simplest form of the two types. Static load balancing is the selection and placement of a logical process on some processing element located on a distributed network. The selection of the processing element for some logical process is based upon some weighting factor for that process, or some kind of workload characterization of the processing elements or of the network topology, possibly both. The process of selecting a processing element for a logical process requesting service may be done with two possible methods, a stateless method or a statebased method. With a stateless method the selection of a processing element is done without regard to any knowledge of the system state. A statebased method of selecting a processing element implies that the selection of a processing element requires knowledge of the system state, either globally, or locally. Global knowledge implies that the state of the all the components of the system is known, and local knowledge implies that only partial knowledge is known. If the state

of the system is needed then some kind of messaging or probing of network resources among the requesting processes, agents, or processing elements is needed to determine their availability. Once a processing element is selected for a logical process, the logical process is executed on the selected processing element for the duration of the logical process lifetime.

Two examples of stateless placement techniques for selecting a processing element for logical processes are round robin and random placement. Round robin placement selects the next processing element from a predefined list. Random placement selects an element randomly from a set of processing elements.

Examples of statebased process placement techniques include greedy algorithms and stochastic selection processes. Greedy processes typically try to find the processing element with the lightest load or the best response time, therefore requiring the process to have some knowledge of the workload of each processing element or the state of the network topology between the client and server. Another example is the selection of a processing element using a randomly selected subset of a set of processing elements and then selecting the processor in the subset with the lowest load. Studies by Mitzenmacher 1997 and Dahlin 1998 researched the random subset selection technique in great detail. Finally, stochastic selection techniques may be used to select a processing element based upon the probability distribution of the server loads. This technique may select any server, but the lighter the load the higher the probability of selecting the server. These techniques are described in detail in Chapter 4.

2.1.2Dynamic Load Balancing

Dynamic load balancing is the initial selection and placement of a logical process on some processing element in a distributed network and then at some point in time there may be a decision made to move a process to some other processing element. The initial selection and placement is done with the same method as static load balancing. But at some point in time during the execution of the logical process, based on some decision criteria, a process may be preempted and migrated to another processing element somewhere else on the network. Generally a process is migrated to another processor if the migration cost or overhead is less than some predetermined metric.

This raises a number of issues regarding dynamic load balancing when the system chooses to move a process. Some of these issues are:

Which process or processes are candidates for migration

Which processing element is the best target for process migration

How do you preserve the process state when it is migrated

Is the system homogeneous or does it have heterogeneous systems

What is the overhead cost of migration

When is the decision for migration made

Who makes the decision to migrate; the system, server or process

CHAPTER ONE

INTRODUCTION

1.1 BACKGROUND OF THE STUDY

Online activities have a recent past replaced virtually every form of transactions. This is because of the advent of the internets which provide a globle network connection for all such activities. With this technology, many institution have their ten lades spread across the globle. In line with this trend, job search activities and job providers need to join the band wagon of the globle community in shearing their their information across internet. The project work is base on the nation .

A web portal, also known as a links page, presents information from diverse sources in a unified way. Apart from the standard search engine feature, web portals offer other services such as Email, news, stock price, information, databases, and entertainment. Portals provid a way for enterprises to provide a consistent look feel with access control and procedures for multiple applications and databases, which otherwise would have been different entities altogether.

1.2 STATEMENT OF THE PROBLEM

Individual website need to be created so that client can access their desired information directly.

The sudden increase in the number of recruitments enroll in each school has transcended the manipulation of the existing system used by the school administrators and this prompted a lot of problems which encompass the inaccurate computation of students result by the staffs on the account of nonavailability of adequate number of computer systems for the computation. This is a very ugly development.

Also, it was very complicated to observe when the enrolment of students should cease since there was no efficient system for the estimation of enrolment ratio to give a signal when the enrolment tends to move beyond the projection. All these and more are encountered due to the debilitation of the prevailing system used. It was very difficult to point out students who cheat in the course of examination as attributed to the nonstandard measure used in the supervision of the examination.

The school complained seriously on the unnecessary stress encountered while making the recruitment enrollment manually.

1.3 OBJECTIVE OF THE STUDY

The practical objective of this work is to design and implement an online recruitment portal, one of the most important objective of this project is to contribute to academic research work while the subsidiary objective include;

To help employers to post their job offer online and their vacant job positions

Providing the possibility for job seekers to build their curriculum vitae CVs online, look for new job opportunities in industries and organizations, get Email notification of interesting job vacancies and apply directly through the website.

To help organizations attract, test, recruit, employ and retain qualify staff with minimal amount of administration.

To reduce or totally remove the malpractice that goes among the recruitment agents or personnel managers.

1.4 SIGNIFICANCE OF THE STUDY

If this prototype is fully developed it will be very useful in many areas such as;

It will ease the work of the personnel department of the any organization.

It will create more employment opportunities for our youth

The government can also review and deploy it to other sectors

Private individuals can also find it interesting

1.5 SCOPE OF THE STUDY

This project will go as far as deploying web technologies in the implementation.

Dreamweaver will be used as the major development tools. Database connection using MySQL will extensively be covered in this work, studies were carried out in the various institutions that conduct interviews and recruitments. The scheme used is closed tag to the information collected at the point of research all forms and database designed followed the pattern of the manual means by the employer of labour.

This project was deployed using a local server which runs on a standalone pc and not deployable to the internet.

1.6 DEFINITION OF TERMS/VARIABLES

Recruitment: this refer to the process of attracting screening qualified people for a job at an organization or firm

Web: a web refers to a vehicle for accessing and sharing of information

Sever: is a computer or program managing access to a resource or service in a network.

Portal: a web application that is designed to represent a ton of information in a concise and centered way there by making the internet easier to use e.g. Yahoo.com, netscape.com etc

Ontology: ontology in computer science and information technology is a formal representation of the knowledge by the set of concept within a domain and the relationship between those concepts.

Metadata: this is loosely defined as data about data. It is concept that applies mainly to electronically archived data and is used to describe the definition structure and administration of data file with all contents in context to ease the use of the captured and archived data for further use.

SQL: Structured Query Language is a database computer language designed for managing data in relational database management system RDBMS and originally base upon relational algebra. It scope include data query and update, schema creation and modification, and date access control.

Database: this is designed to offer an organized Mechanism for storing managing and retrieving information.

Dreamweaver: this is a proprietary web development applications originally create by macromedia; it is now developed by adobe system which acquired macromedia in 2005

Markup: this implies inserting keys or codes into a web document as desired when web user download the web page.

CHAPTER ONE

1.0 Introduction

This project is on Design and implementation of drug verification system using GSM. Products are created by brand owners and handed to third parties contract manufacturer, shipping company, distributor for delivery to merchants for later sale to consumers. These products can range from commodity items e.g., flour to limited quantity luxury items e.g., designer handbags to one of a kind items e.g., original artwork. Counterfeit products are often created and sold as the real thing. Counterfeits leverage the original brand but generally have less overhead due to some combination of lower quality, reduced marketing expenses, reduced support costs and/or reduced corporate expenses ranging from lower labor costs to failure to pay tariffs.

The three main parties brand owner, merchant and consumer are affected differently by the distribution of counterfeits. Consumers either willingly purchase counterfeits at a lower cost or are tricked into buying a counterfeit thinking they are getting authentic merchandise. In the former case they are generally happy, at least initially. The latter case, in some instances, may have little effect, i.e., the consumer may have overpaid for an item. However, more damaging effects may be realized if the product malfunctions. These effects can range from lack of recourse since the product is not covered by the warranty of the brand owner or manufacturer to physical harm in the case of food, prescription drugs, mechanical equipment, etc. Merchants and third parties may unknowingly or willingly participate in the distribution of counterfeit products. Brand owners suffer both hard decreased profit and soft brand erosion losses from counterfeit products.

This research work describes a system that enables brand owners, merchants and consumers to verify the authenticity of a product. It analyzes the different avenues of attack and presents three potential implementations of the system based upon the motivation of the participants and the cost of implementation. The research assumes the reader is acquainted with the production and distribution of counterfeit products.

1.1 Background of the Study

With the majority of the worlds population seeking required medications for various illnesses and medical conditions day in day out, there is a need for appropriate pharmaceutical drugs. The agencies responsible for regulating and approving these pharmaceutical drugs are doing their best to provide the general population with at least a yearly update of all registered drugs approved for various distributions at local drug stores, hospital pharmacies, private pharmacies and licensed chemical sellers. However, due to challenging factors such as cost of production, middlemen distribution, research and legal issues, accessibility and reliable source of sale, there have been more issues arising from the illegal and unregistered pharmaceutical drugs. There is also no guarantee of an individual seeking medical help through the use of prescription drugs. Records gained after each annual registration will be made available and it will provide the various stakeholders with information regarding pharmaceutical drugs allowed for regulation on the local drug markets and the also the manufacturers responsible for each drug distribution. The stakeholders to make use of the information available include manufacturers, medical institutions, pharmacies and pharmaceutical drug importers, distributors and the general public. The provision or availability of the system will help the public to be aware of the pharmaceutical drugs that have being approved by the authority in charge. Also, to improve the quality of life by the healthcare community and life in general, and awareness of unregistered and/or fake pharmaceutical drugs to the public and stakeholders. This information of registered pharmaceutical drugs needs to be integrated and made accessible to the majority of population to enable them to view for themselves Gostin, Lawrence O. Over the years, a number of hybrid solutions have been applied to this problem. In general, they can be classified as employing a combination of stepped up regulatory enforcement and technological innovation. Being pioneers in technology, industrialized nations have typically enjoyed a good balance between these two key ingredients Home, W. H. O.

Developing nations, however, are comparatively less endowed and generally not in the position to invest vast amounts in the research and development needed to yield effective anti-counterfeit technologies. Thus, where such countries have chosen to tackle the unregistered pharmaceutical drug problem, stepped up regulatory enforcement syndicated raids and legal proceedings is the only deployable tool. Fortunately, the need for technological assistance to the enforcement only approach has been identified, and innovators in the first world have developed a number of products. Technologies like Nanoparticle taggant, RFID tags and UV sensitive labels, all require new training and expensive readers currently not present on the developing nation market. Holograms are the leading anti-counterfeit measure, but the mature technology is currently subject to routine counterfeiting due to low cost reproduction equipment. All these solutions will not give the consumer control in checking the validity of the drugs at the point of sale, but a system that can be with them, such as an online system for checking registered pharmaceutical drugs, will aid to an extent Gillian J. Buckley. As users of pharmaceutical drugs, being able to identify these unregistered and fake drugs has become very challenging in recent times. What baffles many is why and how some of these fake pharmaceutical drugs find their way on to the market without the knowledge and approval of the FDA. Some even believe that to cover their incompetence, the FDA, once in a while, picks on one of the local companies simply to give the impression that it is working. In a statement issued on October 8, 2013, Imani Ghana said the FDA could not absolve itself from the apparent retrogressing in quality terms of products by the pharmaceutical companies as it has failed to ramp up its own internal capacity to lift up Ghanaian pharmaceutical companies.http://www.ghanaweb.com/ There is also the belief that the regulators have to review the processes involved in the registration of pharmaceutical drugs in the country including, but not limited to, evaluation of documents/dossiers, average throughput time for registration, risk/analytical assessment reports of pharmaceutical drugs, the entry and clearance of pharmaceutical product at the various points of entry. The Food and Drugs Authority occasionally publishes list of registered drugs but by then the harm of these unregistered pharmaceutical drugs will/have already crippled our healthcare system and markets. Interestingly, most of these companies have advertisements of the apparently fake drugs running on radio, television and in newspapers on daily basis. As a result, there are so many ways of ascertaining the availability of particular pharmaceutical drugs at any drug outlet. This leads to situations where majority of the population seeking healthcare solutions to variety of health problems not being able to cure themselves efficiently and effectively. There is currently no centralized system of checking list of registered and unregistered pharmaceutical drugs when needed. Depending on the locality of the user, he/she can research for himself/herself if a drug being purchased is registered and has fulfilled all necessities needed to distribute and sell to the Ghanaian population

1.2 Statement of Problem

The major and core issue that gave rise to this research work, is on the fact that most of the pharmaceutical drug users seek to use original product but because fake of counterfeit drugs now, do not let one differentiate from the original anymore, and the process of verifying a product currently is not encouraging because it will take much time and before then, the ill person is supposed to take his medication, which is to say that the verification process is slow and not reliable as sometimes you don’t get thee feedback at all. This issue is what the research seek to resolve by developing a secure and reliable system that can function better than the previous one.

1.3 Objective of the Study

The basic objective of the project is to provide simpler means to the consumer and regulatory agencies for establishing drug authentication and protect the consumers health and life safety. In achieving the objective, following goals have been set:

Web based portal / SMS based system / Mobile App enabling the citizens to check the authenticity of the drugs online, Tracking and tracing of the drug where manufactured to ensure the reliable supply of drugs to consumers for patient safety and brand protection of manufacturer as well as nation, the information like Name of Drug, Name of Manufacturer, Batch number, Date of manufacturing, Date of expiry, Usage of drug optional and Composition of drug optional, to be provided online to the consumer, Provide necessary support to the regulatory agencies in prevention of counterfeiting, fraud and illegal sale of drugs.

1.4 Significance of the Study

This thesis will present in a precise manner, the importance of drugs validity and authenticity to our health. It is believed that if this research wok in full implemented will help reduce the rate of counterfeit in drugs production and uses among individual. It is also expected that the study will benefit the manufacturers of this drugs that is the original company and industry because they will have more sales as the citizens will go for the original one and the fake will have no sales in the market anymore.

The software developed from this study will be useful to the end users or the customers in helping them to verify the drugs they buy for medication. It is expected that the findings will expose the fake drug sellers in the market and they production companies. By this exposure, the pharmaceutical industry will learn more and stand by manufacturing quality products. It is possible that by this outcome the fake pharmaceutical industries will realistically adjust to the standard of production approved by the world Health Organization WHO.

Subsequently, it will go a long way to enhance the computer science students effectiveness in the society by being capable of carrying out what they have learned, thereby contributing to the building up of the society at the local, national and international levels.

The research will also be beneficial to the researcher. This is because the study will expose the researcher to so many related areas in the course of carrying out his research. This will enhance the researchers experience, knowledge and understanding on real live application and solution solving techniques.

1.5 Project Study Scope

The Drug verification system and authentication system project is an initiative of the researcher to ensure the genuineness and authenticity of the drugs used within the country imported from any part of the country to ours Nigeria basically imported from India and for citizens in the domestic market. The project covers all the drugs sold in our country Nigeria.

1.6 Limitation of the Study

The challenges of implementing this system and its cost are details below.

a. Diversity of Pharmaceutical Industry

Nigerian Pharmaceutical drugs comes mostly from the Indian Pharma industry, having more than 20,000 registered units which are highly fragmented with severe price competition and government price control. There are approximately 250 large units and more than 8,000 small and medium scale units, which form the core of the Pharmaceutical industry in India. The large units are highly qualified technically as well as professionally. On the other hand, the medium and small manufacturers will not afford to implement this system a drug verification information system DVI system. So this will be a core challenge to the implementation of this system.

b. Implementation of method for unique identification of the product

There are various active and passive technologies available like RFID, 1D or 2D Bar Codes, Hologram, Forensic taggants Optical taggants , Microparticle taggants nano taggants etc. To implement a robust and effective solution to achieve both objectives Drug Authentication and Verification, there was a need of globally accepted solution for uniquely identification of the product which is easily accessible, less space consuming for printing and cost effective for its all three levels of packaging namely Primary, Secondary and Tertiary. Primary is the package which is in direct physical contact with the active ingredient, Secondary is the carton containing one or more primary packs including a mono carton containing one primary pack and Tertiary means a shipper containing one or more secondary packs.

c. Financial Implications and over heads for the manufacturers

The financial implications and investment for the implementation of the system was major concern of the Pharma Industry specially for small and medium scale manufacturers in the country.

1.7 Definition of Terms

Database: A collection of logically related data to meet the information need of organization.

GSM: Global System for Mobile communication.

DBMS: Database Management Software that enable the user to define, maintain Control the database.

Application Program: A computer program that interacts with the database.

MENU: This is a list of options presented on the screen with each option identified by short code followed by longer description of its purposes.

Drug: It is referred to as a medicine or chemical substances that are administered to Patientsfor curative measures.

Pharmacy: A placed in a hospital where medicine or chemical substances are kept, stored and prepared.

Flowchart: A diagram that shows connection between the different stages of process of the system.

Relation: A relation is a named table with columns and rows Attribute; An attributes is a named column of a Relation Domain: A set of allowable values for one or more table

Database design: The process of creating a design that will support emprise mission statement and mission required database e system.

Software: These are program for computer which allows certain specific task to be accomplished e.g. word process etc.

Hardware: Computer equipment used to perform input processing and system output activates.

Management information system: collection of people, database, and devices produced to use in providing routine information to manager and decision makers of the organization.

ABSTRACT

Artificial intelligence has enabled the development of more sophisticated and more efficient student models which represent and detect a broader range of student behavior than was previously possible. In this research, the implementation of a user-friendly software tool for predicting the students performance in course which is based on a neural network classifier will be made. This tool has a simple interface and can be used by an educator for classifying students and distinguishing students with low achievements or weak students who are likely to have low achievements. The observed poor quality of graduates of students of this institution in recent times has been partly traced to inadequacies of some or most of the lecturer in the University which goes down to ability to handle the students. In this study an Artificial Neural Network ANN model, for predicting the likely performance of student will be developed and tested. The system will be developed and trained using data spanning five generations of graduates from one of the department in the school. The use of artificial intelligence has enabled the development of more sophisticated and more efficient student models which represent and detect a broader range of student behaviour than was previously possible.

Due to the platform which this system will run on, it will be developed using the Artificial Intelligence Markup Language, therefore, I will deploy this system using C for its development.

CHAPTER ONE

1.0INTRODUCTION

During the last few years, the application of artificial intelligence in education has grown exponentially, spurred by the fact that it allows us to discover new, interesting and useful knowledge about students. Educational data mining EDM is an emerging discipline, concerned with developing methods for exploring the unique types of data that come from educational context. While traditional database queries can only answer questions such as find the students who failed the examinations, data mining can provide answers to more abstract questions like find the students who will possibly succeed the examinations. One of the key areas of the application of EDM is the development of student models that would predict student characteristics or performances in their educational institutions. Hence, researchers have begun to investigate various data mining methods to help educators to evaluate and improve the structure of their course context.

The main objective of the admission system is to determine candidates who would likely do well in the university or can perform well within the academic year or to produce students of high grade and intelligence. The quality of candidates admitted into any higher institution affects the level of research and training within the institution, and by extension, has an overall effect on the development of the country itself, as these candidates eventually become key players in the affairs of the country in all sectors of the economy.

Recently, however, there has been a noticeable slide in the quality of graduates of some Nigerian universities. The inadequacies of the present university admission system, among other factors, have been blamed for this decline. Due to the increasing gap between the numbers students seeking admission and the total available admission slots, there has been a corresponding increased pressure on the process. This pressure has lead to rampant cases of admission fraud and related problems.

In Nigeria, students are required to enter secondary school after spending a minimum of six years of Primary Education and passing a prescribed National Common Entrance Examination. A student then spends a minimum period of six years in Secondary School at the end of which he or she takes the General Certificate of Education Examination GCE, also known as the Senior Secondary Certificate Examination SSCE or the Ordinary Level Exams. A maximum of nine and a minimum of seven subjects are registered for in the examination with Mathematics and English Language being compulsory. Nine possible grades are obtainable for each subject; these are A1, A2, A3 distinctions grades C4, C5, C6, credit grades, P7, P8 pass grades, and F9 Failure.

Hence this study takes an engineering approach to tackling the problem of admissions by seeking ways to make the process more effective and efficient. Specifically the study seeks to explore the possibility of using an Artificial Neural Network model to predict the performance of a student before admitting the student.

Intuitively one expects the performance of a student to be a function of some number of factors parameters relating to the background and intelligence of said student. It is however obvious that it will be quite difficult finding an analytical or a mathematical model that may acceptably model this performance/factors relationship. However one practical approach for predicting the performance of a student may be by extrapolating from historical data of past students background and their associated performances.

The drawback here is the difficulty of selecting an appropriate function capable of capturing all forms of data relationships as well as automatically modifying output in case of additional information, because the performance of a candidate is influenced by a number of factors, and this influence/relationship is not likely going to be any simple known regression model.

An artificial neural network, which imitates the human brain in problem solving, is a more general approach that can handle this type of problem. Hence, our attempt to build an adaptive system such as the Artificial Neural Network to predict the performance of a candidate based on the effect of these factors.

The results of this prediction can also be used by instructors to specify the most suitable teaching actions for each group of students, and provide them with further assistance tailored to their needs. In addition, the prediction results may help students develop a good understanding of how well or how poorly they would perform, and then develop a suitable learning strategy. Accurate prediction of student achievement is one way to enhance the quality of education and provide better educational services Romero and Ventura, 2007. Different approaches have been applied to predicting student academic performance, including traditional mathematical models and modern data mining techniques. In these approaches, a set of mathematical formulas was used to describe the quantitative relationships between outputs and inputs i.e., predictor variables. The prediction is accurate if the error between the predicted and actual values is within a small range

1.1 BACKGROUND OF THE RESEARCH

In machine learning and cognitive science, artificial neural networks ANNs are a family of statistical learning models inspired by biological neural networks the central nervous systems of animals, in particular the brain and are used to estimate or approximate functions that can depend on a large number of inputs and are generally unknown. Artificial neural networks are generally presented as systems of interconnected neurons which exchange messages between each other. The connections have numeric weights that can be tuned based on experience, making neural nets adaptive to inputs and capable of learning. For example, a neural network for handwriting recognition is defined by a set of input neurons which may be activated by the pixels of an input image. After being weighted and transformed by a function determined by the networks designer, the activations of these neurons are then passed on to other neurons. This process is repeated until finally, an output neuron is activated. This determines which character was read.

The artificial neural network ANN, a soft computing technique, has been successfully applied in different fields of science, such as pattern recognition, fault diagnosis, forecasting and prediction. However, as far as we are aware, not much research on predicting student academic performance takes advantage of artificial neural network. Kanakana and Olanrewaju 2001 utilized a multilayer perception neural network to predict student performance. They used the average point scores of grade 12 students as inputs and the first year college results as output. The research showed that an artificial neural network based model is able to predict student performance in the first semester with high accuracy. A multiple feed forward neural network was proposed to predict the students final achievement and to classify them into two groups. In their work, a student achievement prediction method was applied to a 10week course. The results showed that accurate prediction is possible at an early stage, and more specifically at the third week of the 10week course.

Advising students on their class performance and motivating them in order to improve on their performance is an integral part of every instruction. The mechanisms to achieve the above aim required a technique capable of accurately predicting student achievement as early as possible and cluster them for better academic assistance. According to Lykourentzou et al, 2009, student achievement prediction can help identify the weak learners and properly assist them to cope with their academic pursuit. Several methods and systems have been developed for the above task, most of which are artificial intelligence based. For instance, Lykourentzou et al., 2009 estimated the final grades of students in e-learning courses with multiple feed forward neural networks using multiple choice test data of students of National Technical University of Athens, Greece as input. The results obtained shows that ANN is 91.2 efficient. Junemann, Lagos, and Arriagada 2007 used neural networks to predict future student schooling performance based on students family, social, and wealth characteristics. The aforementioned work focused on predicting the achievement of 15yearold secondary students on reading, mathematics and science subjects in Berlin.

In the Nigeria context, Oladokun, Adebanjo amp; CharlesOwaba 2008 applied multilayer perceptron neural network for predicting the likely performance of candidates being considered for admission into Engineering Course of the University of Ibadan using various influencing factors such as ordinary level subjects scores, matriculation exam scores, age on admission, parental background etc., as input variables. The results showed that ANN model is able to correctly predict the performance of more than 70 of prospective students.

However, Abass et al., 2011 applied another technique of Artificial Intelligence AI i.e., casebase reasoning CBR to predict student academic performance based on the previous datasets using 20 students in the Department of Computer Science, TASUED as the study domain. The high correlation coefficient observed between the actual graduating CGPA and the CBR predicted ones also justify the usefulness and effectiveness of AI techniques in this type of task.

In this research work, Artificial Neural Network is used to estimate students final grade in the university with a prediction level of 92.

1.2STATEMENT OF RESEARCH PROBLEM

Looking into the institution this days, you will discover that 48 of the student are actually performing very low on their academic level, whom if asked to defend his admission status cannot i.e. sitting for the attitude test, when proper investigation is carried out, findings shows that most of them have their way into the school through bribe or the so called upper hand. Also another issue or problem for this research work is that some of the applied candidates, some are actually sound and capable of performing well when admitted, but because of some factors at the moment or surrounding the student, prevent the student from obtaining or securing his admission into the school. With this little problem I seek to develop a neural network system an artificial one that will solve this problem. Coupled with the stress gone through during the admission and delay in the process that ends up not being done perfect to the standard required.

The observed poor academic performance of some Nigerian students tertiary and secondary in recent times has been partly traced to inadequacies of the National University Admission Examination System. It has become obvious that the present process is not adequate for selecting potentially good students. Hence there is the need to improve on the sophistication of the entire system in order to preserve the high integrity and quality. It should be noted that this feeling of uneasiness of stakeholders about the traditional admission system, which is not peculiar to Nigeria, has been an age long and global problem. Kenneth Mellamby 1956 observed that universities worldwide are not really satisfied by the methods used for selecting undergraduates. While admission processes in many developed countries has benefited from, and has been enhanced by, various advances in information science and technology, the Nigerian system has yet to take full advantage of these new tools and technology. Hence this study takes an scientific approach to tackling the problem of admissions by seeking ways to make the process more effective and efficient. Specifically the study seeks to explore the possibility of using an Artificial Neural Network model to predict the performance of a student before admitting the student.

1.3 OBJECTIVES OF THE STUDY

The primary aim of my research work is to develop an artificial neural network system that will be capable of predicting student performance.

Some other objectives which I will be covering in this research work are as follows:

1.A system that will enhance the admission process of this institution in terms of admitting the right student into the institution.

2.An easy and friendly user interface ANNs which will allow fast operation and analysis of student output.

3.To determine some suitable factors that affect a students performance.

4.To model an artificial neural network that can be used to predict a candidates performance based on given pre requirement data given to it.

1.4 SIGNIFICANCE OF THE STUDY

This study will educate on the design and implementation of Artificial Neural Network. It will also educate on how Artificial Neural Network can be used in predicting students academic performance.

This research will also serve as a resource base to other scholars and researchers interested in carrying out further research in this field subsequently, if applied will go to an extent to provide new explanation to the topic

Also the system is essential to be developed and implemented in this institution, its significant will promote the image of this university, help the institution in making the proper decision as to whom to admit or knowing ones capability and performance, implementing this system will encourage any applicant to study in the best atmosphere so as to bring the best out of him before seeking for admission into this institution. The chances of frauds, briberies and corruption will be reduce ass each student will be tested be the system and not human. The new system saves and reduce cost of carrying admission test or grading student performance.

1.5SCOPE OF THE STUDY

The research is limited or only covers on the use of artificial neural network in predicting student performance on their academic using fountain university Ogun State Nigeria. Also, the simulation of the artificial neural network will be done using a data of five years period and learning skills.

1.6LIMITATION OF THE STUDY

During the course of performing/researching this project work, the researcher encountered a lot of challenges as well as opposition which ranges from financial constraints, time factor, sourcing of material etc. this factors in their own ways, slowed down the speedy progress of this work that resulted to the researcher not being able to finish the research work on time as is required

1.7DEFINITION OF TERMS

NONPROFIT ORGANIZATION: A nonprofit organization or organization surplus income to the organizations shareholders

REFERENCES

1 C.M. Bishop. Neural Networks for Pattern Recognition. Oxford, 1995.

2 Ayan, M.N.R.; Garcia, M.T.C. 2013. Prediction of university students academic achievement by linear and logistic models. Span. J. Psychol. 11, 275288.

3 Kanakana, G.M.; Olanrewaju, A.O. 2001. Predicting student performance in engineering education using an artificial neural network at Tshwane university of technology. In Proceedings of the International Conference on Industrial Engineering, Systems Engineering and Engineering Management for Sustainable Global Development, Stellenbosch, South Africa, 2123 September 2011; pp. 17.

4 Romero, C.; Ventura, S. 2007, Educational Data mining: A survey from 1995 to 2005. Expert Syst. Appl. 33, 135146.

5 Ting, S.R. 2008, Predicting academic success of first year engineering students from standardized test scores and psychosocial variables. Int. J. Eng. Educ., 17, 7580.

6 G. Brown, A. Pocock, M.J. Zhao, and M. Lujan. Conditional likelihood maximization: A unifying framework for information theoretic feature selection. Journal of Machine Learning Research, 13:2766, 2012.

7 W. Cohen. Fast effective rule induction. In International Conference on Machine Learning, pages 115123, 1995.

8 P. Domingos and M. Pazzani. On the optimality of the simple Bayesian classifier under zeroone loss. Machine Learning, 29:103130, 1997.

9 M.T. Hagan and M.B. Menhaj. Training feed forward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, 56:989993, 1994.

10 S. Haykin. Neural Networks: A Comprehensive Foundation. Macmillan College Publishing Company, New York, 1994.

11 R. Kohavi. A study of cross validation and bootstrap for accuracy estimation and model selection. In IEEE International Joint Conference on Artificial Intelligence, pages 223228. AAAI Press and MIT Press, 1995.

12 B. Lerner, H. Guterman, M. Aladjem, and I. Dinstein. A comparative study of neural network based feature extraction paradigms. Pattern Recognition Letters, 201:714, 1999.

13 I.E. Livieris, M.S. Apostolopoulou, D.G. Sotiropoulos, S. Sioutas, and P. Pintelas. Classification of large biomedical data using ANNs based on BFGS method. In 13th Panellenic Conference of Informatics, pages 8791, 2009.

14 I.E. Livieris and P. Pintelas. An improved spectral conjugate gradient neural network training algorithm. International Journal on Artificial Intelligence Tools, 211, 2012.

CHAPTER TWO

LITERATURE REVIEW

2.0 INTRODUCTION

According to Owojori 2002, review of literature on a research study